def strings_split_v1(input=None, sep=None, maxsplit=-1, # pylint: disable=redefined-builtin
result_type="SparseTensor", source=None, name=None):
"""Split elements of `input` based on `sep`.
Let N be the size of `input` (typically N will be the batch size). Split each
element of `input` based on `sep` and return a `SparseTensor` or
`RaggedTensor` containing the split tokens. Empty tokens are ignored.
Examples:
```python
>>> tf.strings.split(['hello world', 'a b c'])
tf.SparseTensor(indices=[[0, 0], [0, 1], [1, 0], [1, 1], [1, 2]],
values=['hello', 'world', 'a', 'b', 'c']
dense_shape=[2, 3])
>>> tf.strings.split(['hello world', 'a b c'], result_type="RaggedTensor")
<tf.RaggedTensor [['hello', 'world'], ['a', 'b', 'c']]>
```
If `sep` is given, consecutive delimiters are not grouped together and are
deemed to delimit empty strings. For example, `input` of `"1<>2<><>3"` and
`sep` of `"<>"` returns `["1", "2", "", "3"]`. If `sep` is None or an empty
string, consecutive whitespace are regarded as a single separator, and the
result will contain no empty strings at the start or end if the string has
leading or trailing whitespace.
Note that the above mentioned behavior matches python's str.split.
Args:
input: `1-D` string `Tensor`, the strings to split.
sep: `0-D` string `Tensor`, the delimiter character.
maxsplit: An `int`. If `maxsplit > 0`, limit of the split of the result.
result_type: The tensor type for the result: one of `"RaggedTensor"` or
`"SparseTensor"`.
source: alias for "input" argument.
name: A name for the operation (optional).
Raises:
ValueError: If sep is not a string.
Returns:
A `SparseTensor` of rank `2`, the strings split according to the delimiter.
The first column of the indices corresponds to the row in `source` and the
second column corresponds to the index of the split component in this row.
"""
source = deprecation.deprecated_argument_lookup(
"input", input, "source", source)
with ops.name_scope(name, "StringSplit", [source]):
sparse_result = string_ops.string_split_v2(
source, sep=sep, maxsplit=maxsplit)
if result_type == "SparseTensor":
return sparse_result
elif result_type == "RaggedTensor":
return ragged_tensor.RaggedTensor.from_value_rowids(
values=sparse_result.values,
value_rowids=sparse_result.indices[:, 0],
nrows=sparse_result.dense_shape[0])
else:
raise ValueError("result_type must be 'RaggedTensor' or 'SparseTensor'.")
def string_split_v2(input, sep=None, maxsplit=-1, name=None): # pylint: disable=redefined-builtin
"""Split elements of `input` based on `sep` into a `RaggedTensor`.
Let N be the size of `input` (typically N will be the batch size). Split each
element of `input` based on `sep` and return a `SparseTensor` or
`RaggedTensor` containing the split tokens. Empty tokens are ignored.
Example:
```python
>>> tf.strings.split('hello world')
<Tensor ['hello', 'world']>
>>> tf.strings.split(['hello world', 'a b c'])
<tf.RaggedTensor [['hello', 'world'], ['a', 'b', 'c']]>
```
If `sep` is given, consecutive delimiters are not grouped together and are
deemed to delimit empty strings. For example, `input` of `"1<>2<><>3"` and
`sep` of `"<>"` returns `["1", "2", "", "3"]`. If `sep` is None or an empty
string, consecutive whitespace are regarded as a single separator, and the
result will contain no empty strings at the start or end if the string has
leading or trailing whitespace.
Note that the above mentioned behavior matches python's str.split.
Args:
input: A string `Tensor` of rank `N`, the strings to split. If
`rank(input)` is not known statically, then it is assumed to be `1`.
sep: `0-D` string `Tensor`, the delimiter string.
maxsplit: An `int`. If `maxsplit > 0`, limit of the split of the result.
name: A name for the operation (optional).
Raises:
ValueError: If sep is not a string.
Returns:
A `RaggedTensor` of rank `N+1`, the strings split according to the
delimiter.
"""
with ops.name_scope(name, "StringSplit", [input]):
input = ragged_tensor.convert_to_tensor_or_ragged_tensor(
input, dtype=dtypes.string, name="input")
if isinstance(input, ragged_tensor.RaggedTensor):
return input.with_flat_values(
string_split_v2(input.flat_values, sep, maxsplit))
rank = input.shape.ndims
if rank == 0:
return string_split_v2(array_ops.stack([input]), sep, maxsplit)[0]
elif rank == 1 or rank is None:
sparse_result = string_ops.string_split_v2(
input, sep=sep, maxsplit=maxsplit)
return ragged_tensor.RaggedTensor.from_value_rowids(
values=sparse_result.values,
value_rowids=sparse_result.indices[:, 0],
nrows=sparse_result.dense_shape[0],
validate=False)
else:
return string_split_v2(
ragged_tensor.RaggedTensor.from_tensor(input), sep, maxsplit)
def string_split_v2(input, sep=None, maxsplit=-1, name=None): # pylint: disable=redefined-builtin
"""Split elements of `input` based on `sep` into a `RaggedTensor`.
Let N be the size of `input` (typically N will be the batch size). Split each
element of `input` based on `sep` and return a `SparseTensor` or
`RaggedTensor` containing the split tokens. Empty tokens are ignored.
Example:
```python
>>> tf.strings.split('hello world')
<Tensor ['hello', 'world']>
>>> tf.strings.split(['hello world', 'a b c'])
<tf.RaggedTensor [['hello', 'world'], ['a', 'b', 'c']]>
```
If `sep` is given, consecutive delimiters are not grouped together and are
deemed to delimit empty strings. For example, `input` of `"1<>2<><>3"` and
`sep` of `"<>"` returns `["1", "2", "", "3"]`. If `sep` is None or an empty
string, consecutive whitespace are regarded as a single separator, and the
result will contain no empty strings at the start or end if the string has
leading or trailing whitespace.
Note that the above mentioned behavior matches python's str.split.
Args:
input: A string `Tensor` of rank `N`, the strings to split. If
`rank(input)` is not known statically, then it is assumed to be `1`.
sep: `0-D` string `Tensor`, the delimiter string.
maxsplit: An `int`. If `maxsplit > 0`, limit of the split of the result.
name: A name for the operation (optional).
Raises:
ValueError: If sep is not a string.
Returns:
A `RaggedTensor` of rank `N+1`, the strings split according to the
delimiter.
"""
with ops.name_scope(name, "StringSplit", [input]):
input = ragged_tensor.convert_to_tensor_or_ragged_tensor(
input, dtype=dtypes.string, name="input")
if isinstance(input, ragged_tensor.RaggedTensor):
return input.with_flat_values(
string_split_v2(input.flat_values, sep, maxsplit))
rank = input.shape.ndims
if rank == 0:
return string_split_v2(array_ops.stack([input]), sep, maxsplit)[0]
elif rank == 1 or rank is None:
sparse_result = string_ops.string_split_v2(
input, sep=sep, maxsplit=maxsplit)
return ragged_tensor.RaggedTensor.from_value_rowids(
values=sparse_result.values,
value_rowids=sparse_result.indices[:, 0],
nrows=sparse_result.dense_shape[0],
validate=False)
else:
return string_split_v2(
ragged_tensor.RaggedTensor.from_tensor(input), sep, maxsplit)
def strings_split_v1(input=None, sep=None, maxsplit=-1, # pylint: disable=redefined-builtin
result_type="SparseTensor", source=None, name=None):
"""Split elements of `input` based on `sep`.
Let N be the size of `input` (typically N will be the batch size). Split each
element of `input` based on `sep` and return a `SparseTensor` or
`RaggedTensor` containing the split tokens. Empty tokens are ignored.
Examples:
>>> print(tf.compat.v1.strings.split(['hello world', 'a b c']))
SparseTensor(indices=tf.Tensor( [[0 0] [0 1] [1 0] [1 1] [1 2]], ...),
values=tf.Tensor([b'hello' b'world' b'a' b'b' b'c'], ...),
dense_shape=tf.Tensor([2 3], shape=(2,), dtype=int64))
>>> print(tf.compat.v1.strings.split(['hello world', 'a b c'],
... result_type="RaggedTensor"))
<tf.RaggedTensor [[b'hello', b'world'], [b'a', b'b', b'c']]>
If `sep` is given, consecutive delimiters are not grouped together and are
deemed to delimit empty strings. For example, `input` of `"1<>2<><>3"` and
`sep` of `"<>"` returns `["1", "2", "", "3"]`. If `sep` is None or an empty
string, consecutive whitespace are regarded as a single separator, and the
result will contain no empty strings at the start or end if the string has
leading or trailing whitespace.
Note that the above mentioned behavior matches python's str.split.
Args:
input: A string `Tensor` of rank `N`, the strings to split. If
`rank(input)` is not known statically, then it is assumed to be `1`.
sep: `0-D` string `Tensor`, the delimiter character.
maxsplit: An `int`. If `maxsplit > 0`, limit of the split of the result.
result_type: The tensor type for the result: one of `"RaggedTensor"` or
`"SparseTensor"`.
source: alias for "input" argument.
name: A name for the operation (optional).
Raises:
ValueError: If sep is not a string.
Returns:
A `SparseTensor` or `RaggedTensor` of rank `N+1`, the strings split
according to the delimiter.
"""
input = deprecation.deprecated_argument_lookup(
"input", input, "source", source)
with ops.name_scope(name, "StringSplit", [input]):
input = ragged_tensor.convert_to_tensor_or_ragged_tensor(
input, dtype=dtypes.string, name="input")
if result_type == "SparseTensor" and input.shape.rank == 1:
return string_ops.string_split_v2(input, sep=sep, maxsplit=maxsplit)
ragged_result = string_split_v2(input, sep=sep, maxsplit=maxsplit)
if result_type == "SparseTensor":
return ragged_result.to_sparse()
elif result_type == "RaggedTensor":
return ragged_result
else:
raise ValueError("result_type must be 'RaggedTensor' or 'SparseTensor'.")
def testSplitV2(self, input, expected, input_is_ragged=False, **kwargs): # pylint: disable=redefined-builtin
# Check that we are matching the behavior of Python's str.split:
self.assertEqual(expected, self._py_split(input, **kwargs))
# Prepare the input tensor.
if input_is_ragged:
input = ragged_factory_ops.constant(input, dtype=dtypes.string)
else:
input = constant_op.constant(input, dtype=dtypes.string)
# Check that the public version (which returns a RaggedTensor) works
# correctly.
expected_ragged = ragged_factory_ops.constant(
expected, ragged_rank=input.shape.ndims)
actual_ragged_v2 = ragged_string_ops.string_split_v2(input, **kwargs)
actual_ragged_v2_input_kwarg = ragged_string_ops.string_split_v2(
input=input, **kwargs)
self.assertAllEqual(expected_ragged, actual_ragged_v2)
self.assertAllEqual(expected_ragged, actual_ragged_v2_input_kwarg)
# Check that the internal version (which returns a SparseTensor) works
# correctly. Note: the internal version oly supports vector inputs.
if input.shape.ndims == 1:
expected_sparse = self.evaluate(expected_ragged.to_sparse())
actual_sparse_v2 = string_ops.string_split_v2(input, **kwargs)
self.assertEqual(expected_sparse.indices.tolist(),
self.evaluate(actual_sparse_v2.indices).tolist())
self.assertEqual(expected_sparse.values.tolist(),
self.evaluate(actual_sparse_v2.values).tolist())
self.assertEqual(
expected_sparse.dense_shape.tolist(),
self.evaluate(actual_sparse_v2.dense_shape).tolist())
def strings_split_v1(source,
sep=None,
maxsplit=-1,
result_type="SparseTensor"):
"""Split elements of `source` based on `sep`.
Let N be the size of source (typically N will be the batch size). Split each
element of `source` based on `sep` and return a `SparseTensor` or
`RaggedTensor` containing the split tokens. Empty tokens are ignored.
Examples:
```python
>>> tf.strings.split(['hello world', 'a b c'])
tf.SparseTensor(indices=[[0, 0], [0, 1], [1, 0], [1, 1], [1, 2]],
values=['hello', 'world', 'a', 'b', 'c']
dense_shape=[2, 3])
>>> tf.strings.split(['hello world', 'a b c'], result_type="RaggedTensor")
<tf.RaggedTensor [['hello', 'world'], ['a', 'b', 'c']]>
```
If `sep` is given, consecutive delimiters are not grouped together and are
deemed to delimit empty strings. For example, source of `"1<>2<><>3"` and
sep of `"<>"` returns `["1", "2", "", "3"]`. If `sep` is None or an empty
string, consecutive whitespace are regarded as a single separator, and the
result will contain no empty strings at the start or end if the string has
leading or trailing whitespace.
Note that the above mentioned behavior matches python's str.split.
Args:
source: `1-D` string `Tensor`, the strings to split.
sep: `0-D` string `Tensor`, the delimiter character.
maxsplit: An `int`. If `maxsplit > 0`, limit of the split of the result.
result_type: The tensor type for the result: one of `"RaggedTensor"` or
`"SparseTensor"`.
Raises:
ValueError: If sep is not a string.
Returns:
A `SparseTensor` of rank `2`, the strings split according to the delimiter.
The first column of the indices corresponds to the row in `source` and the
second column corresponds to the index of the split component in this row.
"""
sparse_result = string_ops.string_split_v2(source,
sep=sep,
maxsplit=maxsplit)
if result_type == "SparseTensor":
return sparse_result
elif result_type == "RaggedTensor":
return ragged_tensor.RaggedTensor.from_value_rowids(
values=sparse_result.values,
value_rowids=sparse_result.indices[:, 0],
nrows=sparse_result.dense_shape[0])
else:
raise ValueError(
"result_type must be 'RaggedTensor' or 'SparseTensor'.")
def testSplitV2(self):
strings = ["pigs on the wing", "animals"]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings)
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [0, 2], [0, 3], [1, 0]])
self.assertAllEqual(values, [b"pigs", b"on", b"the", b"wing", b"animals"])
self.assertAllEqual(shape, [2, 4])
def testSplitV2(self):
strings = ["pigs on the wing", "animals"]
tokens = string_ops.string_split_v2(strings)
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [0, 2], [0, 3], [1, 0]])
self.assertAllEqual(values, [b"pigs", b"on", b"the", b"wing", b"animals"])
self.assertAllEqual(shape, [2, 4])
ragged_tokens = ragged_string_ops.string_split_v2(strings)
self.assertAllEqual(ragged_tokens.row_splits, [0, 4, 5])
self.assertAllEqual(ragged_tokens.values,
[b"pigs", b"on", b"the", b"wing", b"animals"])
def testSplitV2EmptySeparatorMaxSplit(self):
# Match Python behavior:
# '1 2 3'.split(maxsplit=1)
# ['1', '2 3']
# >>> " 4 5 6 ".split(maxsplit=1)
# ['4', '5 6 ']
strings = ["1 2 3", " 4 5 6 "]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings, maxsplit=1)
indices, values, shape = sess.run(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [1, 0], [1, 1]])
self.assertAllEqual(values, [b"1", b"2 3", b"4", b"5 6 "])
self.assertAllEqual(shape, [2, 2])
def testSplitV2SimpleSeparatorMaxSplit(self):
# Match Python behavior:
# >>> '1,2,3'.split(',', maxsplit=1)
# ['1', '2,3']
# >>> '4,5,,6,'.split(',', maxsplit=1)
# ['4', '5,,6,']
strings = ["1,2,3", "4,5,,6,"]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings, sep=',', maxsplit=1)
indices, values, shape = sess.run(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [1, 0], [1, 1]])
self.assertAllEqual(values, [b"1", b"2,3", b"4", b"5,,6,"])
self.assertAllEqual(shape, [2, 2])
def testSplitV2EmptySeparatorMaxSplit(self):
# Match Python behavior:
# '1 2 3'.split(maxsplit=1)
# ['1', '2 3']
# >>> " 4 5 6 ".split(maxsplit=1)
# ['4', '5 6 ']
strings = ["1 2 3", " 4 5 6 "]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings, maxsplit=1)
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1],
[1, 0], [1, 1]])
self.assertAllEqual(values, [b"1", b"2 3", b"4", b"5 6 "])
self.assertAllEqual(shape, [2, 2])
def testSplitV2SimpleSeparatorMaxSplit(self):
# Match Python behavior:
# >>> '1,2,3'.split(',', maxsplit=1)
# ['1', '2,3']
# >>> '4,5,,6,'.split(',', maxsplit=1)
# ['4', '5,,6,']
strings = ["1,2,3", "4,5,,6,"]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings, sep=',', maxsplit=1)
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1],
[1, 0], [1, 1]])
self.assertAllEqual(values, [b"1", b"2,3", b"4", b"5,,6,"])
self.assertAllEqual(shape, [2, 2])
def testSplitV2EmptySeparator(self):
# Match Python behavior:
# >>> '1 2 3'.split()
# ['1', '2', '3']
#>>> ' 1 2 3 '.split()
#['1', '2', '3']
strings = ["1 2 3", " 4 5 6 "]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings)
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [0, 2],
[1, 0], [1, 1], [1, 2]])
self.assertAllEqual(values, [b"1", b"2", b"3", b"4", b"5", b"6"])
self.assertAllEqual(shape, [2, 3])
def testSplitV2SimpleSeparator(self):
# Match Python behavior:
# >>> '1,2,3'.split(',')
# ['1', '2', '3']
# >>> '1,2,,3,'.split(',')
# ['1', '2', '', '3', '']
strings = ["1,2,3", "4,5,,6,"]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings, sep=',')
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [0, 2],
[1, 0], [1, 1], [1, 2], [1, 3], [1, 4]])
self.assertAllEqual(values, [b"1", b"2", b"3",
b"4", b"5", b"", b"6", b""])
self.assertAllEqual(shape, [2, 5])
def testSplitV2(self,
input,
expected,
input_is_ragged=False,
**kwargs): # pylint: disable=redefined-builtin
# Check that we are matching the behavior of Python's str.split:
self.assertEqual(expected, self._py_split(input, **kwargs))
# Prepare the input tensor.
if input_is_ragged:
input = ragged_factory_ops.constant(input, dtype=dtypes.string)
else:
input = constant_op.constant(input, dtype=dtypes.string)
# Check that the public version (which returns a RaggedTensor) works
# correctly.
expected_ragged = ragged_factory_ops.constant(
expected, ragged_rank=input.shape.ndims)
actual_ragged_v1 = ragged_string_ops.strings_split_v1(
input, result_type="RaggedTensor", **kwargs)
actual_ragged_v1_input_kwarg = ragged_string_ops.strings_split_v1(
input=input, result_type="RaggedTensor", **kwargs)
actual_ragged_v1_source_kwarg = ragged_string_ops.strings_split_v1(
source=input, result_type="RaggedTensor", **kwargs)
actual_ragged_v2 = ragged_string_ops.string_split_v2(input, **kwargs)
actual_ragged_v2_input_kwarg = ragged_string_ops.string_split_v2(
input=input, **kwargs)
self.assertRaggedEqual(expected_ragged, actual_ragged_v1)
self.assertRaggedEqual(expected_ragged, actual_ragged_v1_input_kwarg)
self.assertRaggedEqual(expected_ragged, actual_ragged_v1_source_kwarg)
self.assertRaggedEqual(expected_ragged, actual_ragged_v2)
self.assertRaggedEqual(expected_ragged, actual_ragged_v2_input_kwarg)
# Check that the internal version (which returns a SparseTensor) works
# correctly. Note: the internal version oly supports vector inputs.
if input.shape.ndims == 1:
expected_sparse = self.evaluate(expected_ragged.to_sparse())
actual_sparse_v1 = ragged_string_ops.strings_split_v1(
input, result_type="SparseTensor", **kwargs)
actual_sparse_v2 = string_ops.string_split_v2(input, **kwargs)
for actual_sparse in [actual_sparse_v1, actual_sparse_v2]:
self.assertEqual(expected_sparse.indices.tolist(),
self.evaluate(actual_sparse.indices).tolist())
self.assertEqual(expected_sparse.values.tolist(),
self.evaluate(actual_sparse.values).tolist())
self.assertEqual(expected_sparse.dense_shape.tolist(),
self.evaluate(actual_sparse.dense_shape).tolist())
def testSplitV2MultiCharSeparator(self):
# Match Python behavior:
# >>> '1<>2<>3'.split('<>')
# ['1', '2', '3']
# >>> "<><>4<>5<><>6<>".split("<>")
# ['', '', '4', '5', '', '6', '']
strings = ["1<>2<>3", "<><>4<>5<><>6<>"]
with self.cached_session() as sess:
tokens = string_ops.string_split_v2(strings, sep="<>")
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(
indices, [[0, 0], [0, 1], [0, 2],
[1, 0], [1, 1], [1, 2], [1, 3], [1, 4], [1, 5], [1, 6]])
self.assertAllEqual(values, [b"1", b"2", b"3",
b"", b"", b"4", b"5", b"", b"6", b""])
self.assertAllEqual(shape, [2, 7])
def testSplitV2EmptySeparatorMaxSplit(self):
# Match Python behavior:
# '1 2 3'.split(maxsplit=1)
# ['1', '2 3']
# >>> " 4 5 6 ".split(maxsplit=1)
# ['4', '5 6 ']
strings = ["1 2 3", " 4 5 6 "]
tokens = string_ops.string_split_v2(strings, maxsplit=1)
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [1, 0], [1, 1]])
self.assertAllEqual(values, [b"1", b"2 3", b"4", b"5 6 "])
self.assertAllEqual(shape, [2, 2])
ragged_tokens = ragged_string_ops.string_split_v2(strings, maxsplit=1)
self.assertAllEqual(ragged_tokens.row_splits, [0, 2, 4])
self.assertAllEqual(ragged_tokens.values, [b"1", b"2 3", b"4", b"5 6 "])
def testSplitV2SimpleSeparatorMaxSplit(self):
# Match Python behavior:
# >>> '1,2,3'.split(',', maxsplit=1)
# ['1', '2,3']
# >>> '4,5,,6,'.split(',', maxsplit=1)
# ['4', '5,,6,']
strings = ["1,2,3", "4,5,,6,"]
tokens = string_ops.string_split_v2(strings, sep=",", maxsplit=1)
indices, values, shape = self.evaluate(tokens)
self.assertAllEqual(indices, [[0, 0], [0, 1], [1, 0], [1, 1]])
self.assertAllEqual(values, [b"1", b"2,3", b"4", b"5,,6,"])
self.assertAllEqual(shape, [2, 2])
ragged_tokens = ragged_string_ops.string_split_v2(
strings, sep=",", maxsplit=1)
self.assertAllEqual(ragged_tokens.row_splits, [0, 2, 4])
self.assertAllEqual(ragged_tokens.values, [b"1", b"2,3", b"4", b"5,,6,"])
def string_split_v2(input, sep=None, maxsplit=-1, name=None): # pylint: disable=redefined-builtin
"""Split elements of `input` based on `sep` into a `RaggedTensor`.
Let N be the size of `input` (typically N will be the batch size). Split each
element of `input` based on `sep` and return a `SparseTensor` or
`RaggedTensor` containing the split tokens. Empty tokens are ignored.
Example:
```python
>>> tf.strings.split(['hello world', 'a b c'])
<tf.RaggedTensor [['hello', 'world'], ['a', 'b', 'c']]>
```
If `sep` is given, consecutive delimiters are not grouped together and are
deemed to delimit empty strings. For example, `input` of `"1<>2<><>3"` and
`sep` of `"<>"` returns `["1", "2", "", "3"]`. If `sep` is None or an empty
string, consecutive whitespace are regarded as a single separator, and the
result will contain no empty strings at the start or end if the string has
leading or trailing whitespace.
Note that the above mentioned behavior matches python's str.split.
Args:
input: `1-D` string `Tensor`, the strings to split.
sep: `0-D` string `Tensor`, the delimiter string.
maxsplit: An `int`. If `maxsplit > 0`, limit of the split of the result.
name: A name for the operation (optional).
Raises:
ValueError: If sep is not a string.
Returns:
A `RaggedTensor` of rank `2`: the strings split according to the delimiter.
"""
with ops.name_scope(name, "StringSplit", [input]):
sparse_result = string_ops.string_split_v2(input,
sep=sep,
maxsplit=maxsplit)
return ragged_tensor.RaggedTensor.from_value_rowids(
values=sparse_result.values,
value_rowids=sparse_result.indices[:, 0],
nrows=sparse_result.dense_shape[0])
def string_split_v2(input, sep=None, maxsplit=-1, name=None): # pylint: disable=redefined-builtin
"""Split elements of `input` based on `sep` into a `RaggedTensor`.
Let N be the size of `input` (typically N will be the batch size). Split each
element of `input` based on `sep` and return a `SparseTensor` or
`RaggedTensor` containing the split tokens. Empty tokens are ignored.
Example:
```python
>>> tf.strings.split(['hello world', 'a b c'])
<tf.RaggedTensor [['hello', 'world'], ['a', 'b', 'c']]>
```
If `sep` is given, consecutive delimiters are not grouped together and are
deemed to delimit empty strings. For example, `input` of `"1<>2<><>3"` and
`sep` of `"<>"` returns `["1", "2", "", "3"]`. If `sep` is None or an empty
string, consecutive whitespace are regarded as a single separator, and the
result will contain no empty strings at the start or end if the string has
leading or trailing whitespace.
Note that the above mentioned behavior matches python's str.split.
Args:
input: `1-D` string `Tensor`, the strings to split.
sep: `0-D` string `Tensor`, the delimiter string.
maxsplit: An `int`. If `maxsplit > 0`, limit of the split of the result.
name: A name for the operation (optional).
Raises:
ValueError: If sep is not a string.
Returns:
A `RaggedTensor` of rank `2`: the strings split according to the delimiter.
"""
with ops.name_scope(name, "StringSplit", [input]):
sparse_result = string_ops.string_split_v2(input, sep=sep,
maxsplit=maxsplit)
return ragged_tensor.RaggedTensor.from_value_rowids(
values=sparse_result.values,
value_rowids=sparse_result.indices[:, 0],
nrows=sparse_result.dense_shape[0])
